Commit graph

5541 commits

Author SHA1 Message Date
ryan-crabbe-berri
a44a58e91a feat(proxy): let team admins edit tpm_limit when a proxy admin enables it
tpm_limit is the first field in the team-admin allow-list registry. The team
settings tab gives a team admin a form with only the enabled fields and sends
only those on save, and UI Settings labels the checkbox the same way
2026-09-16 15:38:30 -07:00
ryan-crabbe-berri
66519da9b6 fix(proxy): report the caller's team edit access on /team/info
The dashboard gated the team settings form on a role it guessed from the
is_* props, the members list and the org list. The org list is premium
gated and empty while loading, so a team admin who is also an org admin
was told team admins cannot edit, although /team/update accepts them as
an org admin

/team/info now returns caller_edit_access, resolved by the same helper
/team/update uses, and TeamInfo keys the form and the toast off that
field. The org list is only read for the organization dropdown now, and
general_settings is read through one validated accessor in both handlers
2026-09-16 15:38:30 -07:00
ryan-crabbe-berri
af0312ba8f refactor(ui): name the admin checks behind the team-admin edit branch
The five-condition chain pushed local/no-long-condition-chain one over its
ceiling and failed the dashboard lint gate.

Claude-Session: https://claude.ai/code/session_018PUCupsaarVLJy4iDFx256
2026-09-16 15:38:06 -07:00
ryan-crabbe-berri
9b77b5c2cb feat(proxy): let proxy admins choose which team fields team admins may edit
Team admins could never reach POST /team/update: the route gate answered
401 before the handler's team-admin branch ran. This moves /team/update
into the self-managed routes, resolves proxy admin, org admin or team
admin inside the handler, and filters team admins through a new
proxy-wide UI setting, team_admin_editable_team_fields. The setting is
an allow-list of team fields. Empty means team admins cannot edit team
settings and get a 403 pointing at the proxy admin, and changing a field
outside the list fails 403 naming that field. Only values that differ
from what is stored count, since the dashboard resends the whole form.

The registry of fields the setting accepts ships empty on purpose. Each
field lands in its own follow-up PR with its value diff and dashboard
wiring. The Admin UI gains a "Team admin editable fields" section under
Settings > UI and a toast on the team page while editing is disabled.

Refs LIT-5722

Claude-Session: https://claude.ai/code/session_01A6SkwJdfZUmkzfUkrEkqX8
2026-09-16 15:38:06 -07:00
ryan-crabbe-berri
9357491f91
Merge pull request #35418 from BerriAI/litellm_skills_ssh_sources
feat(ui): accept ssh clone urls when registering a skill
2026-09-16 15:36:18 -07:00
Yassin Kortam
f62f140f75
Merge pull request #41403 from BerriAI/litellm_key_total_spend
feat(proxy): expose lifetime total_spend on virtual keys
2026-09-16 14:49:02 -07:00
Yassin Kortam
2bfa10b6d9
Merge pull request #41311 from BerriAI/litellm_key_status_filter_deleted_lookup
feat(keys): filter /key/list by active, expired, revoked or deleted status and serve deleted keys from /key/info
2026-09-16 14:48:34 -07:00
Yassin Kortam
95abc9fb0b
Merge pull request #41330 from BerriAI/litellm_team_model_max_budget_v2
feat(team): team-level model_max_budget with key-level overrides
2026-09-16 14:48:29 -07:00
Yassin Kortam
314c0d71a5
Merge pull request #41327 from BerriAI/litellm_s3_log_prompts_only
feat(s3): add s3_log_prompts_only option to log prompts without responses
2026-09-16 14:48:18 -07:00
ryan
2bb478fb59 fix(ui): keep http and upper-case https skill sources clickable on the detail page
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-16 18:45:11 +00:00
ryan
7cd6869cfa test(ui): match skill source links by exact name so codeql stops flagging the host regexes
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-16 18:40:10 +00:00
ryan-crabbe-berri
ecd72c51da refactor(ui): register ssh skill sources verbatim and share the https host rules
The ssh parser rebuilt the clone url it was given, stripping a trailing .git and
appending one back. Git treats that suffix as optional, and the hosts whose clone
paths are not org/repo break when it is forced on, so an Azure DevOps v3 or a
CodeCommit v1/repos url registered through the form would no longer clone.

It also carried its own host pattern, which demanded an alphabetic final label and
so rejected internal hosts like gitlab.internal.k8s2 that the https path accepts.

Rewrite the scp form into an ssh:// url purely to validate it, reuse the https host
and credential checks through a shared isSafeHost, and store exactly what the user
typed. Only a url that survives the round trip unchanged is accepted, which is what
keeps traversal segments out of the feed, so the two ssh regexes, the dots-only
guard and the clone-url builders all collapse into one function.
2026-09-16 11:29:25 -07:00
yassin
6cf35ed71b feat(proxy): expose lifetime total_spend on virtual keys
Adds a persistent total_spend column to LiteLLM_VerificationToken and LiteLLM_DeletedVerificationToken, incremented in the same write as spend and left alone by budget resets. Surfaces it on /key/info, /key/list and the Admin UI Virtual Keys table and key detail view

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-16 09:42:20 +00:00
Tin Chi Lo
9d640b86ed fix(ui): simplify Capability and Fuse routing options 2026-09-15 20:58:38 -07:00
tin-berri
3b14631f06
Merge pull request #41315 from BerriAI/litellm_capability_fuse_classifier_ui
feat(ui): configure capability and Fuse v2 classifiers
2026-09-15 20:13:57 -07:00
Tin Chi Lo
39b7812810 feat(ui): configure capability and Fuse v2 classifiers 2026-09-15 19:30:50 -07:00
yucheng-berri
41eb2dbfeb
Merge pull request #41128 from BerriAI/litellm_llm_judge_pre_call
feat(guardrails): support pre_call and during_call modes for llm_as_a_judge
2026-09-15 18:58:21 -07:00
Yassin Kortam
67cb0bc089
Merge pull request #41313 from BerriAI/litellm_model_activity_response_time
feat(ui): show average response time per model in usage model activity
2026-09-15 18:43:48 -07:00
yassin
d8ef940232 chore(ui): regenerate schema.d.ts for organization_id on archived key records
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-16 01:06:36 +00:00
yucheng
77a6327675 feat(guardrails): support pre_call and during_call modes for llm_as_a_judge
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-16 01:05:52 +00:00
ryan
b3432abef7 refactor(ui): derive the ssh skill name from the bare repo path
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-16 00:58:03 +00:00
ryan
b0ed6c8d89 merge main into litellm_skills_ssh_sources and re-apply ssh source parsing on the shadcn skill form
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-16 00:57:30 +00:00
yucheng
9bd3f7b885 Merge remote-tracking branch 'origin/main' into litellm_agent365_mcp_guardrail 2026-09-16 00:52:27 +00:00
yassin
260ff5f491 feat(team): team-level model_max_budget with key-level overrides
A team can now carry a per-model budget map that every key on the team
inherits. A key's own model_max_budget entry for the same model takes
precedence, so it is gated on and billed to the key alone.

Backend: NewTeamRequest/UpdateTeamRequest accept model_max_budget (validated
like the key-level field, enterprise gated); the value is hydrated onto
UserAPIKeyAuth via the token view, TeamGrants and the carried budget state;
_check_team_model_budget enforces it in the centralized common checks; the
limiter meters spend under team_model_spend:<team>:<model>:<duration> and
skips the team counter when the key overrides; /team/update lets only a
proxy admin raise, re-window or drop a cap; /team/info exposes usage.
The Anthropic context-management compaction summary subrequest runs the
same team gate. Both fallback token-view SQL definitions project the column.

UI: team create and edit forms reuse the key-level ModelMaxBudgetEditor,
premium gated, sending {} to clear and omitting unchanged fields.

A key entry overrides the team cap only when it spend-gates the model
(non-negative max_budget); a row that only carries tpm/rpm limits or a
negative cap leaves the team cap in force.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-16 00:40:58 +00:00
Mateo Wang
aa710dc6a9
Merge pull request #35388 from BerriAI/litellm_session_total_duration
fix(spend): sum multi-round session duration in logs UI
2026-09-15 17:31:41 -07:00
Yassin Kortam
7eeba69016
Merge pull request #41316 from BerriAI/litellm_nvidia_nim_infer_passthrough
feat(proxy): add /nvidia_nim passthrough route for NIM object detection and OCR /v1/infer
2026-09-15 17:28:25 -07:00
ryan-crabbe-berri
f34a6eda92
Merge pull request #41294 from BerriAI/litellm_usage_export_gating
fix(ui): block usage export and flag the range when a spend page fails
2026-09-15 17:19:38 -07:00
yassin
251aeea97d fix(ui): show the S3 label when editing the s3_v2 callback
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-15 23:56:31 +00:00
mateo-berri
790c9ab77d test(ui): name the session column fixtures so the inline-object lint budget holds
Some checks failed
ai-gateway image / ai-gateway release image (push) Has been cancelled
LiteLLM Rust / rust-lint (push) Has been cancelled
Terraform Provider / gofmt, vet, build, test (push) Has been cancelled
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Has been cancelled
LiteLLM Rust / rust-test (push) Has been cancelled
Terraform Modules / fmt, validate, test (aws) (push) Has been cancelled
Terraform Modules / fmt, validate, test (gcp) (push) Has been cancelled
2026-09-15 16:25:01 -07:00
ryan-crabbe-berri
69c3212220 fix(ui): gate the usage export on range coverage, not on a fetch being in flight
A loading flag only flips once the fetch effect runs, so the render right after a
date or filter change still reported the previous range as loaded and let an export
read its rows. Stamp the completed range on the hook and compare it during render
instead, the way the tiles already do.

Also stop the failure banner claiming a page loaded when the first request is what
failed, which left it reading 1/1.
2026-09-15 16:21:37 -07:00
mateo-berri
3441f73118 Merge remote-tracking branch 'origin/main' into litellm_session_total_duration
# Conflicts:
#	litellm/proxy/spend_tracking/spend_management_endpoints.py
#	tests/test_litellm/proxy/spend_tracking/test_spend_management_endpoints.py
#	ui/litellm-dashboard/src/components/view_logs/RequestLogsTableColumns.tsx
#	ui/litellm-dashboard/src/components/view_logs/columns.tsx
2026-09-15 16:17:18 -07:00
yassin
f6f782ff67 feat(s3): add s3_log_prompts_only option to log prompts without responses
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-15 23:11:44 +00:00
tin-berri
8cd00d2d6e
Merge pull request #41282 from BerriAI/litellm_fast_mode_toggle_0915
Some checks failed
Unit Tests: Proxy DB Operations / auth-checks (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / budgets (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / custom-logging (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / proxy-utils (push) Blocked by required conditions
Unit Tests / misc (push) Waiting to run
Unit Tests / proxy-auth (push) Waiting to run
Unit Tests / proxy-endpoints (push) Waiting to run
Unit Tests: Proxy DB Operations / db-and-spend (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / endpoints-and-responses (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / guardrails-hooks (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / jwt-and-keys (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / key-generation (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / logging-misc (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / proxy-runtime (push) Blocked by required conditions
Unit Tests: Proxy DB Operations / proxy-server-core (push) Blocked by required conditions
Unit Tests / caching-local (push) Waiting to run
Unit Tests / core-utils (push) Waiting to run
Unit Tests / enterprise-package (push) Waiting to run
Unit Tests / enterprise-routing (push) Waiting to run
Unit Tests / integrations (push) Waiting to run
Unit Tests / All Other Providers (push) Waiting to run
Unit Tests / Vertex AI (push) Waiting to run
Unit Tests / proxy-extras (push) Waiting to run
Unit Tests / proxy-infra (push) Waiting to run
Unit Tests / proxy-server (push) Waiting to run
Unit Tests / responses-caching-types (push) Waiting to run
GitHub Actions Security Analysis / zizmor (push) Waiting to run
Terraform Provider / gofmt, vet, build, test (push) Has been cancelled
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Has been cancelled
ai-gateway image / ai-gateway release image (push) Has been cancelled
feat(auto-router): add per-model Fast mode toggle
2026-09-15 16:10:06 -07:00
Yassin Kortam
0bb95e298c
Merge pull request #41309 from BerriAI/litellm_playground_custom_request_headers 2026-09-15 15:56:22 -07:00
Yassin Kortam
9d75cdd502
Merge pull request #41304 from BerriAI/litellm_lit1698_openai_system_messages_first 2026-09-15 15:56:13 -07:00
Yassin Kortam
9bb83fdaea
Merge pull request #41281 from BerriAI/litellm_lit_7417_jwt_key_mapping_issuer_scope
fix(jwt-auth): scope JWT key mappings by issuer to prevent cross-issuer collisions
2026-09-15 15:51:50 -07:00
Yassin Kortam
eec954bf9a
Merge pull request #41296 from BerriAI/litellm_models_table_url_state
feat(ui): persist Models table search, filters, sort and page in the URL
2026-09-15 15:46:27 -07:00
yassin
be082013f7 fix(ui): label the response time chart tooltip with the series name
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-15 22:38:55 +00:00
yassin
ebb9a3ceeb chore(ui): regenerate schema.d.ts for the /nvidia_nim passthrough route
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-15 22:34:59 +00:00
yassin
754e87fa67 fix(ui): keep gateway auth and content-type headers ahead of playground custom headers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-15 22:24:13 +00:00
yassin
5b0fa89056 feat(ui): show average response time per model in usage model activity
Roll request_duration_ms of successful, non-internal requests into the
daily spend tables as total_response_time_ms plus timed_requests, expose
both through the daily activity endpoints, and derive the average in the
Usage -> Model Activity view of the Admin UI

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-15 22:16:12 +00:00
yassin
c05af7a12f feat(ui): add custom request headers to the API Playground
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-15 22:12:06 +00:00
yassin
6c8b9a7b05 feat(keys): filter /key/list by active, expired, revoked or deleted status and serve deleted keys from /key/info
Persist and expose the lifecycle of API keys so spend, audit and FinOps
workflows can still resolve a key after it is revoked, expires or is
deleted.

/key/list?status= now accepts active, expired and revoked next to the
existing deleted value. revoked means blocked=true, expired means not
blocked with a past expiry, active is the rest, so the three values
partition the live key table. deleted keeps reading the
LiteLLM_DeletedVerificationToken archive.

/key/info falls back to that archive when the key is no longer in the
live table, running the same owner/team/org authorization check, and
every response now carries a derived status field. The hashed token is
still stripped.

The Virtual Keys page gets a Status filter (URL-persisted) and a Deleted
badge that shows when and by whom the key was deleted.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-15 22:12:01 +00:00
yassin
99fa38504a fix(ui): bound Models table page, page size and sort_by read from the URL
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-15 21:55:07 +00:00
yassin
77d913958d feat(openai): add openai_system_messages_first to put system messages first for prompt caching
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-15 21:53:29 +00:00
tin-berri
ce1a4f896a
Merge pull request #41272 from BerriAI/litellm_fuse_v2_classifier_pr
feat(router): add Fuse V2 classifier after capability forecasting
2026-09-15 14:43:44 -07:00
yassin
868d3855ab feat(ui): persist Models table search, filters, sort and page in the URL
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-15 21:37:09 +00:00
ryan-crabbe-berri
9b35954347 fix(ui): block usage export and flag the range when a spend page fails
The Usage page drains the daily activity endpoint page by page. A page that
threw was only logged to the console: the loading banner disappeared, the
partial totals stayed on screen looking final, and Export Data stayed
clickable, so the CSV handed to finance was silently short.

The hook now reports `failed`, PaginationStatusAlerts renders it as an error
banner naming how many pages actually loaded, and the export is blocked with
the reason on hover while the data on screen does not cover the range.
2026-09-15 14:10:23 -07:00
Yassin Kortam
e54b93017b fix(jwt-auth): scope JWT key mappings by issuer to prevent cross-issuer collisions 2026-09-15 21:02:17 +00:00
Yassin Kortam
e6af62aaac
Merge pull request #40997 from BerriAI/litellm_batch_tpd_limit
feat(proxy): add tpd_limit (tokens per day) for batch submissions
2026-09-15 13:39:45 -07:00